Prompt Cards

Design a DAG (Airflow/Prefect) for reproducible research: crawl→retrieve→synthesize→verify→export. Include artifact hashing and cache invalidation rules.

Create an exporter that converts answers into JSON/CSV with fields (claim,evidence,source_url,confidence,timestamp). Provide schemas and sample exports.

Specify table extraction, PDF figure capture, and caption grounding. Define when to quote vs paraphrase, and include a screenshot-to-citation workflow.

Design watchers for tracked topics that diff sources and trigger re-summaries when material changes occur. Provide noise filters and notification policy.

Create a pipeline that generates questions from documents, with required answer spans and citations. Provide filters for ambiguity and leakage checks.

Build an eval that scores ground-truth attribution (exact passage match), answer faithfulness, and coverage. Provide dataset schema and a nightly regression plan.

Propose a router that routes by budget and SLA: small model for recall, larger for synthesis, tools only when signal warrants. Provide policy examples and guardrails.

Create a memory layer that stores hypotheses, decisions, and unresolved questions. Provide schemas, TTL rules, and a notebook export (Markdown/CSV).

Design a UI: inline citations, hover previews, source quality badges, and ‘expand to passage’. Include keyboard flows and accessibility specs (WCAG). Output wireframes and event schema.

Specify constrained modes with scope limits, consent prompts, guideline links, and mandatory citation density. Provide refusal templates and domain-specific disclaimers.

Create a cross-lingual flow: detect language, translate queries, use multilingual embeddings, and cite in user language while preserving original quotes. Provide locale heuristics and typography rules.

Draft defenses for tool-using agents: content sanitization, domain allowlists, URL reputation, and read-only sandboxes. Provide red-team prompts and pass/fail gates.